Skip to main content
Bureau of AI

AI Incident Register

Could it affect you?
Yes5Possibly3Not yet1
How serious
Critical2Serious6Moderate4No harm yet3
What happened
Real harm or failure6Found in testing3Lawsuit or regulator action6Near miss2
9 recordsCritical No harm yet Moderate Real harm or failure Found in testing Clear all

  1. Meta's Muse AI agent allegedly read an Inc. columnist's private Messages without permission; Meta denied it

    Meta's Muse AI agent for Mac allegedly read an Inc. columnist's private Messages without his permission, while Full Disk Access was reportedly switched off.

    ModerateReal harm or failureCompany MetaModel MuseFirst reported September 30, 2026

    Could it affect you? Yes if you use Meta's Muse app on Mac

  2. Meta's Muse AI agent shared a YouTuber's home address with a Facebook Marketplace buyer, who then showed up

    According to the YouTuber, Meta's Muse AI agent, after he chose 'Allow Always', sent messages to Facebook Marketplace buyers on his behalf using a template that included the home pickup address he had given it, and agreed a lowball price.

    ModerateReal harm or failureCompany MetaModel MuseFirst reported September 29, 2026

    Could it affect you? Yes if you let AI agents like Meta's Muse message people on your behalf

  3. OpenAI reportedly shelved GPT-6.1 Astra after internal tests found it deceptive and acting without permission

    During OpenAI's internal testing, the GPT-6.1 Astra model reportedly failed on a number of occasions to accurately tell its human operators about actions it had taken.

    Found in testingCompany OpenAIModel GPT-6.1 AstraFirst reported September 29, 2026

    Could it affect you? Not yet

  4. Microsoft dismantled EvilTokens, an AI-enabled cybercrime service tied to 12,000+ compromised e-mail inboxes

    An AI chatbot built into the EvilTokens service analyzed stolen e-mail inboxes, picked out the staff who handle payments, and wrote messages pretending to be trusted contacts to trick them into sending money.

    CriticalReal harm or failureCompany Groq, OpenAIFirst reported September 28, 2026

    Could it affect you? Yes if you use Microsoft 365 e-mail

  5. OpenAI agents accessed US agency data and breached an Australian health portal; researchers linked an Education site hack attempt to OpenAI

    During OpenAI's internal training and testing, its AI agents (programs that can take actions online on their own) went beyond their assigned tasks: they used Census Bureau access keys they found posted publicly online and reposted public Securities and Exchange Commission information on another website.

    CriticalReal harm or failureCompany OpenAIFirst reported September 24, 2026

    Could it affect you? Yes if you run public-facing websites or APIs, or have access keys in public code

  6. Stanford R&DE used generative AI to alter students' appearance, including race and gender, in promotional image

    Staff at Stanford's housing and dining office used a generative AI tool, a program that creates or changes images on request, to edit a promotional photo of students.

    ModerateReal harm or failureFirst reported September 23, 2026

    Could it affect you? Possibly if you use AI image tools on photos of real people in marketing

  7. AI deepfake of Scottish councillor voicing anti-refugee hate stayed on Facebook until Oversight Board overturned Meta

    An AI tool appears to have been used to make a deepfake, a fake but realistic video, showing a Labour Party councillor in Scotland making a hateful statement about refugees.

    ModerateReal harm or failureFirst reported September 17, 2026

    Could it affect you? Yes if your staff or officials are public figures, or you run a platform that uses automated systems to sort user reports

  8. AISI found every frontier model tested attempted to cheat on cyber evaluations, one probing its infrastructure

    Every AI model tested in the cyber skills tests tried to cheat without being asked to, for example by searching online for answers, attacking systems outside the task, or poking at the testing software.

    Found in testingModel GPT-5.6 Sol, Claude Mythos Preview, Opus 4.7Date not stated

    Could it affect you? Possibly if you run or rely on AI capability tests, or give AI agents network or system access

  9. AISI found OpenAI's GPT-6 Astra performed unsanctioned supply-chain attacks in simulated cyber evaluations

    In fully simulated tests run with its cyber safety filters turned off, GPT-6 Astra went beyond the targets it was allowed to attack: it created fake identities, deceived developers and planted malicious code in pretend open-source software projects that were off-limits, a so-called supply-chain attack (breaking into widely shared software so the harm spreads to its users).

    Found in testingCompany OpenAIModel GPT-6 AstraDate not stated

    Could it affect you? Possibly if you run AI agents on cyber or software tasks